Intelligent classification system for concrete compressive strength

Abstract Artificial intelligence and its diverse applications are examples of emerging new technologies that have so far been shown to be successful in merging scientific applications. Generally, intelligent systems outperform their traditional counterparts in solving non-linear tasks. Artificial neural network (ANN) models are usually designed and used to arbitrate these non-linear problems; as they mimic the structure and function of a biological brain. In this paper, an intelligent classification system is proposed to decide the result of a routine and laborious civil engineering quality control process. The ANN model is specifically designed, implemented and tested in order to classify the compressive strength grade of different concrete mixes as low, normal or high strength. Concrete elements of varying compressive strength classes and qualities, are required to be used for different purposes and under different environmental conditions. The grade of the concrete’s strength is highly dependent on many non-linear factors and it is often conventionally determined by using civil engineering methods involving the destruction of concrete samples. Our aim is to classify the concrete strength without destructing any samples. Experimental results in this work show high efficiency in correctly classifying the compressive strength.

[1]  Adnan Khashman,et al.  Intelligent Face Recognition: Local Versus Global Pattern Averaging , 2006, Australian Conference on Artificial Intelligence.

[2]  Adnan Khashman.  Blood Cell Identification Using a Simple Neural Network , 2008, Int. J. Neural Syst..

[3]  Rajendra Kumar Sharma,et al.  Prediction of Compressive Strength of Concrete Using Artificial Neural Network and Genetic Programming , 2016 .

[4]  Adnan Khashman,et al.  Anticipation of Political Party Voting Using Artificial Intelligence , 2016 .

[5]  James L Noland,et al.  Computer-Aided Structural Engineering (CASE) Project: Decision Logic Table Formulation of ACI (American Concrete Institute) 318-77 Building Code Requirements for Reinforced Concrete for Automated Constraint Processing. Volume 1. , 1986 .

[6]  I-Cheng Yeh,et al.  Modeling of strength of high-performance concrete using artificial neural networks , 1998 .

[7]  Hsing-Chih Tsai,et al.  Modeling concrete strength with high-order neural networks , 2016, Neural Computing and Applications.

[8]  Dejan Vasovic,et al.  Prediction model for compressive strength of basic concrete mixture using artificial neural networks , 2014, Neural Computing and Applications.

[9]  Hasbi Yaprak,et al.  Prediction of the effect of varying cure conditions and w/c ratio on the compressive strength of concrete using artificial neural networks , 2011, Neural Computing and Applications.

[10]  Mohd Saleh Jaafar,et al.  Application of Artificial Neural Networks to Predict Compressive Strength of High Strength Concrete , 2011 .

[11]  Adnan Khashman,et al.  Arbitration of Turkish Agricultural Policy Impact on CO2 Emission Levels Using Neural Networks , 2016 .

[12]  Khandaker M. A. Hossain,et al.  Regression and artificial neural network models for strength properties of engineered cementitious composites , 2016, Neural Computing and Applications.

[13]  Iskender Akkurt,et al.  Prediction of compressive strength of heavyweight concrete by ANN and FL models , 2010, Neural Computing and Applications.

[14]  Adnan Khashman,et al.  Non-Destructive Prediction of Concrete Compressive Strength Using Neural Networks , 2017, ICCS.

[15]  Umit Atici,et al.  Prediction of the strength of mineral admixture concrete using multivariable regression analysis and an artificial neural network , 2011, Expert Syst. Appl..

[16]  K. Sathiyakumari,et al.  Prediction of the Compressive Strength of High Performance Concrete Mix using Tree Based Modeling , 2010 .